Downloads · 30 days
25
29% of all-time downloads
GLM-4-32B-0414-Q4_K_M-ling-lang
taellinglin/GLM-4-32B-0414-Q4_K_M-ling-lang
GLM-4-32B-0414-Q4_K_M-ling-lang is a text generation model from taellinglin. Use it when you need the model to write or continue text. The card lists the license as mit.
zai-org/GLM-4-32B-0414, QLoRA fine-tuned on the Ling programming language — syntax, the full multilingual keyword table (15 languages), the ling- crate ecosystem, real builtin functions, real game-code idioms, and the…
All-time downloads
85
Public
Repo size
19.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf19.7 GB · 100%
At a glance
- Task
- Text Generation
- License
- mit
- Access
- Public
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026
- SHA
- 9abf1c9b
Try a prompt
Base models
Model card
From the Hugging Face model README
GLM-4-32B-0414-Q4_K_M-ling-lang
zai-org/GLM-4-32B-0414, QLoRA fine-tuned on the
Ling programming language — syntax, the full multilingual keyword table
(15 languages), the ling-* crate ecosystem, real builtin functions, real game-code idioms, and
the ling CLI/build system — then merged and quantized to GGUF (Q4_K_M) for llama.cpp /
candle-transformers inference.
Serves chat.ling-lang.org, running fully in-process inside
ling.exe itself via ling-ai's candle-transformers integration (no external model server).
Training data: taellinglin/ling-lang-chat-sft.
Usage
Chat template follows GLM-4's <|user|> / <|assistant|> turn format. Load with llama.cpp,
candle-transformers' quantized GLM4 module, or any GGUF-compatible runtime.
- Task
- Text Generation
- License
- mit
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026